FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2891716277> ?p ?o ?g. }

• W2891716277 abstract "In this paper, a new offline actor-critic learning algorithm is introduced: Sampled Policy Gradient (SPG). SPG samples in the action space to calculate an approximated policy gradient by using the critic to evaluate the samples. This sampling allows SPG to search the action-Q-value space more globally than deterministic policy gradient (DPG), enabling it to theoretically avoid more local optima. SPG is compared to Q-learning and the actor-critic algorithms CACLA and DPG in a pellet collection task and a self play environment in the game this http URL. The online game this http URL has become massively popular on the internet due to intuitive game design and the ability to instantly compete against players around the world. From the point of view of artificial intelligence this game is also very intriguing: The game has a continuous input and action space and allows to have diverse agents with complex strategies compete against each other. The experimental results show that Q-Learning and CACLA outperform a pre-programmed greedy bot in the pellet collection task, but all algorithms fail to outperform this bot in a fighting scenario. The SPG algorithm is analyzed to have great extendability through offline exploration and it matches DPG in performance even in its basic form without extensive sampling." @default.
• W2891716277 created "2018-09-27" @default.
• W2891716277 creator A5016131956 @default.
• W2891716277 creator A5060596453 @default.
• W2891716277 creator A5075211761 @default.
• W2891716277 creator A5087691512 @default.
• W2891716277 date "2018-09-15" @default.
• W2891716277 modified "2023-09-26" @default.
• W2891716277 title "Sampled Policy Gradient for Learning to Play the Game Agar.io" @default.
• W2891716277 cites W1522301498 @default.
• W2891716277 cites W1757796397 @default.
• W2891716277 cites W2064675550 @default.
• W2891716277 cites W2100677568 @default.
• W2891716277 cites W2101539915 @default.
• W2891716277 cites W2103496339 @default.
• W2891716277 cites W2119324175 @default.
• W2891716277 cites W2121863487 @default.
• W2891716277 cites W2136064843 @default.
• W2891716277 cites W2141559645 @default.
• W2891716277 cites W2145339207 @default.
• W2891716277 cites W2173248099 @default.
• W2891716277 cites W2201581102 @default.
• W2891716277 cites W2754517384 @default.
• W2891716277 cites W2790380320 @default.
• W2891716277 cites W2984109677 @default.
• W2891716277 cites W3011120880 @default.
• W2891716277 cites W3103780890 @default.
• W2891716277 cites W2131600418 @default.
• W2891716277 cites W3089091950 @default.
• W2891716277 hasPublicationYear "2018" @default.
• W2891716277 type Work @default.
• W2891716277 sameAs 2891716277 @default.
• W2891716277 citedByCount "5" @default.
• W2891716277 countsByYear W28917162772019 @default.
• W2891716277 countsByYear W28917162772020 @default.
• W2891716277 countsByYear W28917162772021 @default.
• W2891716277 crossrefType "posted-content" @default.
• W2891716277 hasAuthorship W2891716277A5016131956 @default.
• W2891716277 hasAuthorship W2891716277A5060596453 @default.
• W2891716277 hasAuthorship W2891716277A5075211761 @default.
• W2891716277 hasAuthorship W2891716277A5087691512 @default.
• W2891716277 hasConcept C110875604 @default.
• W2891716277 hasConcept C111919701 @default.
• W2891716277 hasConcept C121332964 @default.
• W2891716277 hasConcept C136764020 @default.
• W2891716277 hasConcept C140779682 @default.
• W2891716277 hasConcept C154945302 @default.
• W2891716277 hasConcept C162324750 @default.
• W2891716277 hasConcept C187736073 @default.
• W2891716277 hasConcept C2524010 @default.
• W2891716277 hasConcept C2778572836 @default.
• W2891716277 hasConcept C2780451532 @default.
• W2891716277 hasConcept C2780791683 @default.
• W2891716277 hasConcept C28719098 @default.
• W2891716277 hasConcept C33923547 @default.
• W2891716277 hasConcept C41008148 @default.
• W2891716277 hasConcept C62520636 @default.
• W2891716277 hasConcept C76155785 @default.
• W2891716277 hasConcept C94915269 @default.
• W2891716277 hasConcept C97541855 @default.
• W2891716277 hasConceptScore W2891716277C110875604 @default.
• W2891716277 hasConceptScore W2891716277C111919701 @default.
• W2891716277 hasConceptScore W2891716277C121332964 @default.
• W2891716277 hasConceptScore W2891716277C136764020 @default.
• W2891716277 hasConceptScore W2891716277C140779682 @default.
• W2891716277 hasConceptScore W2891716277C154945302 @default.
• W2891716277 hasConceptScore W2891716277C162324750 @default.
• W2891716277 hasConceptScore W2891716277C187736073 @default.
• W2891716277 hasConceptScore W2891716277C2524010 @default.
• W2891716277 hasConceptScore W2891716277C2778572836 @default.
• W2891716277 hasConceptScore W2891716277C2780451532 @default.
• W2891716277 hasConceptScore W2891716277C2780791683 @default.
• W2891716277 hasConceptScore W2891716277C28719098 @default.
• W2891716277 hasConceptScore W2891716277C33923547 @default.
• W2891716277 hasConceptScore W2891716277C41008148 @default.
• W2891716277 hasConceptScore W2891716277C62520636 @default.
• W2891716277 hasConceptScore W2891716277C76155785 @default.
• W2891716277 hasConceptScore W2891716277C94915269 @default.
• W2891716277 hasConceptScore W2891716277C97541855 @default.
• W2891716277 hasOpenAccess W2891716277 @default.
• W2891716277 hasRelatedWork W109043541 @default.
• W2891716277 hasRelatedWork W1899406468 @default.
• W2891716277 hasRelatedWork W2048306919 @default.
• W2891716277 hasRelatedWork W2081814701 @default.
• W2891716277 hasRelatedWork W2115422932 @default.
• W2891716277 hasRelatedWork W2418933646 @default.
• W2891716277 hasRelatedWork W2566287236 @default.
• W2891716277 hasRelatedWork W2755694566 @default.
• W2891716277 hasRelatedWork W2901024945 @default.
• W2891716277 hasRelatedWork W2912716415 @default.
• W2891716277 hasRelatedWork W2918543091 @default.
• W2891716277 hasRelatedWork W2931942906 @default.
• W2891716277 hasRelatedWork W2950893049 @default.
• W2891716277 hasRelatedWork W2964056654 @default.
• W2891716277 hasRelatedWork W2980366500 @default.
• W2891716277 hasRelatedWork W3014358192 @default.
• W2891716277 hasRelatedWork W3084241738 @default.
• W2891716277 hasRelatedWork W3113493262 @default.
• W2891716277 hasRelatedWork W3160366202 @default.
• W2891716277 hasRelatedWork W940504451 @default.

• next